运用主题词／副主题词关联规则在医学文献 检索系统中抽取知识的尝试  

An Exploratory Research of Knowledge Acquisition with MeSH Heading/Subheading Association Rules in Medline System

作　　者：崔雷 [1] 李丹 [2] 冯博 [3] 

机构地区：[1]中国医科大学信息管理与信息系统学系(医学),沈阳,110001 [2]中国医科大学教务处,沈阳,110001 [3]海军总医院信息科,北京,100037

出　　处：《情报学报》2005年第6期657-662,共6页Journal of the China Society for Scientific and Technical Information

基　　金：教育部人文社会科学规划项目，国家科研项目

摘　　要：本文尝试根据书目文献数据库中主题词/副主题词之间的语义关联规则抽取知识.以阿斯匹林这一比较常用的药物作为文献集合的主题范围,选取经过验证的关联规则,将其运用到具体的文献之中,获得具体的药物与疾病之间的知识,并对这些知识进行检验,以评价这种知识挖掘方式的可靠性.We explored the method of knowledge acquisition by the semantic association rules among the subject heading/ subheadings in a medical bibliographic system. A common drug-aspirin was used as a subject field of the literature set, a proved association rule was used upon the literature, knowledge about this drug and diseases is acquired. We compared the aquired knowledge with those of an authority pharmacopoeia to evaluate the reliability of this method.

关 键 词：知识抽取 关联规则 主题词 医学文献检索系统 

分 类 号：G254.2[文化科学—图书馆学] TP18[自动化与计算机技术—控制理论与控制工程]